autopilot SKILL.md skillA

autopilot from kanevry/session-orchestrator is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kanevry/session-orchestrator/autopilot@git:20261011.76ef0a1

Pins git:20261011.76ef0a1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
kanevry/session-orchestrator
Path
skills/autopilot/SKILL.md
Versions recorded
15
Latest version
git:20261011.76ef0a1, committed Oct 11, 2026
First version recorded
Jun 10, 2026
Size
29,695 bytes
Repository stars
53
License
MIT

Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan → wave-executor → session-end for N iterations with all 10 kill-switches (SPIRAL, FAILED wave, carryover > 50%, max-hours, max-sessions, resource-overload, token-budget, stall-timeout, sub-threshold confidence, user-abort). Reads Mode-Selector output (Phase B) to decide auto-execute vs. fallback. Writes one autopilot.jsonl record per loop run. Phase C scaffold (issue #277); implementation…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Autopilot Skill

## Invocation

The user invokes `/autopilot` with arguments: **$ARGUMENTS**. This is autonomous
session-orchestration mode — a top-level invocation only, never from inside a running
session.

Parse `$ARGUMENTS` before anything else. Unrecognized flags are ignored; out-of-range
values silently clamp to bounds. Use `parseFlags` from `scripts/lib/autopilot.mjs` for
canonical parsing — never re-implement clamping inline. The loop flags
(`--max-sessions`, `--max-hours`, `--confidence-threshold`, `--dry-run`) and their
defaults/bounds are tabled once in § Command Surface below. Two further flags belong to
the invocation surface only:

| Flag | Default | Meaning |
|------|---------|---------|
| `--headless` | `false` | Run via the standalone driver `scripts/autopilot.mjs`, which spawns `claude -p '/session <mode>'` as a child process per iteration. Required for unattended walk-away mode. Without it, `/autopilot` runs the in-process driver inside the current chat session (see § Production Wiring). |
| `--verbose` | `false` | Verbose driver output. |

### Headless (`claude -p`)

Headless requirements:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kanevry/session-orchestrator/autopilot@sha256:6ada4b775e9add8d

The line at the top of this page pins the label git:20261011.76ef0a1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wtw4pz64lxb2w4qf.svg)](https://markdownregistry.com/a/art_wtw4pz64lxb2w4qf)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 15 versions of this file, between Jun 10, 2026 and Oct 11, 2026, about one every 9 days.

versioncommittedcommitsizeaudit
git:20261011.76ef0a1 latest2026-10-11 76ef0a1 29,695 BA view · diff
git:20261002.2166afa2026-10-02 2166afa 29,617 BA view · diff
git:20261002.88a2c7a2026-10-02 88a2c7a 29,496 BA view · diff
git:20261001.4e3072d2026-10-01 4e3072d 29,263 BA view · diff
git:20260930.d3aa8122026-09-30 d3aa812 28,467 BA view · diff
git:20260927.65618562026-09-27 6561856 28,132 BA view · diff
git:20260925.c99f57d2026-09-25 c99f57d 28,113 BA view · diff
git:20260918.20a4cbf2026-09-18 20a4cbf 27,623 BA view · diff
git:20260917.a4e6d252026-09-17 a4e6d25 26,809 BA view · diff
git:20260916.3ebf0e92026-09-16 3ebf0e9 25,199 BA view · diff
git:20260906.ac8b5442026-09-06 ac8b544 23,205 BA view · diff
git:20260828.7daa3d22026-08-28 7daa3d2 24,811 BA view · diff
git:20260708.8f98a542026-07-08 8f98a54 24,501 BA view · diff
git:20260619.c6e34e12026-06-19 c6e34e1 24,421 BA view · diff
git:20260610.c5f76272026-06-10 c5f7627 20,831 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (29695 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

kanevry/session-orchestrator · 53 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wtw4pz64lxb2w4qf
GET https://markdownregistry.com/api/v1/resolve?ref=kanevry/session-orchestrator/autopilot
GET https://markdownregistry.com/api/v1/blob/6ada4b775e9add8dd85a4658cbb13e7df5277e7573448cecd89cfbec21d85846

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from kanevry/session-orchestrator

architecture SKILL.md skill
kanevry/session-orchestrator · .agents/skills/architecture/SKILL.md · Use when the user asks to improve architecture, find refactoring opportunities, surface deepening opportunities…
git:20261003.c34ec50 · audit A · 53 stars
autopilot SKILL.md skill
kanevry/session-orchestrator · .agents/skills/autopilot/SKILL.md · Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan →…
git:20260919.176b605 · audit A · 53 stars
bootstrap SKILL.md skill
kanevry/session-orchestrator · .agents/skills/bootstrap/SKILL.md · Use this skill when scaffolding the minimum repository structure required by session-orchestrator. Invoked…
git:20260919.176b605 · audit A · 53 stars
brainstorm SKILL.md skill
kanevry/session-orchestrator · .agents/skills/brainstorm/SKILL.md · Use when you have a feature idea but the scope or UX is still ambiguous — runs a lightweight Socratic design dialogue…
git:20260919.176b605 · audit A · 53 stars
claude-md-drift-check SKILL.md skill
kanevry/session-orchestrator · .agents/skills/claude-md-drift-check/SKILL.md · Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository…
git:20261003.c34ec50 · audit A · 53 stars
close SKILL.md skill
kanevry/session-orchestrator · .agents/skills/close/SKILL.md · End session with verification, commits, and documentation
git:20260919.176b605 · audit A · 53 stars
convergence-monitoring SKILL.md skill
kanevry/session-orchestrator · .agents/skills/convergence-monitoring/SKILL.md · Monitor iterative improvement loops for convergence. Three signals — shrinking diff, pass-rate plateau, velocity —…
git:20260919.176b605 · audit A · 53 stars
debug SKILL.md skill
kanevry/session-orchestrator · .agents/skills/debug/SKILL.md · Use when encountering any bug, test failure, build break, or unexpected behavior — runs a 4-phase systematic debugging…
git:20260919.176b605 · audit A · 53 stars
discovery SKILL.md skill
kanevry/session-orchestrator · .agents/skills/discovery/SKILL.md · Use this skill when running systematic quality discovery and issue detection. Runs modular probes adapted to the…
git:20260919.176b605 · audit A · 53 stars
dispatcher SKILL.md skill
kanevry/session-orchestrator · .agents/skills/dispatcher/SKILL.md · Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates…
git:20260919.176b605 · audit A · 53 stars
docs-orchestrator SKILL.md skill
kanevry/session-orchestrator · .agents/skills/docs-orchestrator/SKILL.md · Use this skill when orchestrating documentation generation and updates within a session. Maps session scope to…
git:20260919.176b605 · audit A · 53 stars
ecosystem-health SKILL.md skill
kanevry/session-orchestrator · .agents/skills/ecosystem-health/SKILL.md · Monitor health across configured service endpoints, CI pipelines, and critical issues. Automatically invoked during…
git:20260919.176b605 · audit A · 53 stars

Every file in kanevry/session-orchestrator

Other files named autopilot

autopilot SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/autopilot/SKILL.md · Full autonomous execution from idea to working code
git:20260927.ed495e6 · audit A · 40,148 stars
autopilot SKILL.md skill
sethgammon/citadel · skills/autopilot/SKILL.md · Intake-to-delivery pipeline. Processes pending items from .planning/intake/: briefs new ideas, executes approved work…
git:20261009.7a64c3f · audit A · 925 stars
autopilot SKILL.md skill
yan-labs/yan-skills · autopilot/SKILL.md · 当用户说“autopilot”“自己搞定”“直接跑到底”,或委托代理调查、实施并验证一个宽泛任务时使用。仅规划、解释或已有明确窄范围的请求,按用户指定范围处理。
git:20260929.a7e7407 · audit A · 225 stars
autopilot SKILL.md skill
kanevry/session-orchestrator · .codex-plugin/skills/autopilot/SKILL.md · Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan →…
git:20260916.3ebf0e9 · audit A · 53 stars
autopilot SKILL.md skill
outlinedriven/outline-driven-development · .devin/skills/autopilot/SKILL.md · Use when a human has an approved delivery plan and wants the full chain run under phase gates. Not for planning…
git:20260905.1f63894 · audit A · 53 stars
autopilot SKILL.md skill
kanevry/session-orchestrator · .cursor/skills/autopilot/SKILL.md · Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan →…
git:20260825.0626387 · audit A · 53 stars
autopilot SKILL.md skill
kanevry/session-orchestrator · .agents/skills/autopilot/SKILL.md · Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan →…
git:20260919.176b605 · audit A · 53 stars
autopilot SKILL.md skill
naimkatiman/continuous-improvement · third-party/oh-my-claudecode/skills/autopilot/SKILL.md · Full autonomous execution from idea to working code
git:20260906.bface5c · audit A · 9 stars

Browse by kind, by grade A, or by owner.